© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16156
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or fragments in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.97
    ulla
    -0.87
    regation
    -0.86
    phia
    -0.84
    ãĤ¨ãĥ«
    -0.79
    iatrics
    -0.79
    onica
    -0.75
    lication
    -0.73
    çīĪ
    -0.72
    apor
    -0.70
    POSITIVE LOGITS
     informative
    1.03
     unpredictable
    1.02
     insightful
    1.01
     witty
    0.97
     inefficient
    0.97
     albeit
    0.96
     efficient
    0.96
     resilient
    0.94
     humorous
    0.93
     wasteful
    0.92
    Activations Density 0.209%

    No Known Activations